Downloads · 30 days
0
linjian257/qwen3vl_32b_minimax_h3_int8_convrot_uncensored-by-linjian257
qwen3vl_32b_minimax_h3_int8_convrot_uncensored-by-linjian257 is a machine learning model from linjian257. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for minimax-h3. The card lists the license as other.
Downloads · 30 days
0
Access
Public
Updated Aug 5, 2026
Repo size
25.8 GB
Likes
63
Trending 3
Click a slice to open those files.
.safetensors25.8 GB · 100%
From the Hugging Face model README
中文 | English
这是一个供 MiniMax-H3 ComfyUI 工作流使用的 Qwen3-VL-32B INT8 TensorWise + ConvRot 社区修改版文本编码器。该版本由 linjian257 从修改后的 BF16 权重量化得到,重点是在保持 ComfyUI 工作流兼容性的同时明显降低权重文件体积。
本文件只是 MiniMax-H3 的文本编码器组件,并不是完整的视频生成模型,也不是可直接在 LM Studio、llama.cpp 或 vLLM 中作为聊天模型加载的完整 Qwen3-VL 模型。
| 项目 | 内容 |
|---|---|
| 文件名 | qwen3vl_32b_minimax_h3_int8_convrot_uncensored-by-linjian257.safetensors |
| 用途 | MiniMax-H3 的 ComfyUI 文本编码器 |
| 量化格式 | INT8 TensorWise + ConvRot |
| ConvRot group size | 256 |
| Scale | FP32、per-channel、沿输出特征轴 |
| 文件大小 | 25,772,287,417 bytes(约 25.77 GB / 24.00 GiB) |
| 总张量数量 | 1,838 |
| 量化权重张量 | 468 |
| ConvRot 张量 | 359(另有 109 个量化张量未旋转) |
| 保留 BF16 张量 | 434 |
| 文本编码器输出 | 第 50 层之后的未归一化隐藏状态 |
| 修改者 | linjian257 |
| 上游仓库 | MiniMaxAI/MiniMax-H3 / Comfy-Org/MiniMax-H3 |
int8_tensorwise,版本 0.1.0per_channel / out_features)model.* 与 visual.* 中选定的二维权重;bias 等不适合量化的张量保持原精度该文件是从 linjian257 制作的 BF16 社区修改版权重重新量化得到的衍生版本,并非官方 qwen3vl_32b_minimax_h3_int8_convrot.safetensors 的改名或逐字节镜像。
“Uncensored”用于区分版本,不代表对所有提示词、语言、输入形式或工作流效果作出保证。
使用支持 MiniMax-H3 及原生 INT8 ConvRot 的较新版本 ComfyUI。如果出现未知量化格式、缺少 weight_scale 或 ConvRot 相关错误,请先更新 ComfyUI 及其依赖。
将文件放入:
ComfyUI/models/text_encoders/
下载 MiniMax-H3 工作流所需的扩散模型和 VAE 文件。官方整理版见 Comfy-Org/MiniMax-H3。
在 CLIPLoader 节点中选择本文件,并保持模型类型为 minimax。
如果 ComfyUI 找不到该文件,请确认它位于 models/text_encoders 而不是 models/checkpoints 或 models/diffusion_models,然后刷新模型列表或重启 ComfyUI。
该版本可能生成冒犯性、危险、违法、误导或不适宜的内容。使用者必须自行评估输出、遵守适用法律和平台规则,并为生成、发布和传播的内容负责。请勿将其用于伤害未成年人、侵犯隐私、欺诈、仇恨、军事或其他违法有害用途。
本权重采用个人娱乐使用许可 v1.0:仅允许个人娱乐、个人学习、非商业研究和非商业测试。未经 linjian257 书面许可,不得用于商业用途、收费服务、商业部署、转售、再分发或转授权。
This is a community-modified and quantized INT8 TensorWise + ConvRot Qwen3-VL-32B text encoder intended for MiniMax-H3 workflows in ComfyUI. It was produced by linjian257 from modified BF16 weights, with the goal of substantially reducing the weight-file size while retaining compatibility with the ComfyUI workflow.
This file is only the text-encoder component of MiniMax-H3. It is not a complete video-generation model and is not a standalone Qwen3-VL chat model that can be loaded directly in LM Studio, llama.cpp, or vLLM.
| Field | Value |
|---|---|
| Filename | qwen3vl_32b_minimax_h3_int8_convrot_uncensored-by-linjian257.safetensors |
| Intended role | ComfyUI text encoder for MiniMax-H3 |
| Quantization | INT8 TensorWise + ConvRot |
| ConvRot group size | 256 |
| Scales | FP32, per-channel, along the output-feature axis |
| File size | 25,772,287,417 bytes (about 25.77 GB / 24.00 GiB) |
| Total tensor count | 1,838 |
| Quantized weight tensors | 468 |
| ConvRot tensors | 359 (109 other quantized tensors are not rotated) |
| BF16 tensors retained | 434 |
| Encoder output | Unnormalized hidden state after layer 50 |
| Modified by | linjian257 |
| Upstream | MiniMaxAI/MiniMax-H3 / Comfy-Org/MiniMax-H3 |
int8_tensorwise, version 0.1.0per_channel / out_features)model.* and visual.*; unsuitable tensors such as biases remain at their source precisionThis is a newly quantized community derivative of the modified BF16 weights produced by linjian257. It is not a rename or byte-identical mirror of the official qwen3vl_32b_minimax_h3_int8_convrot.safetensors file.
“Uncensored” distinguishes this release and does not guarantee identical behavior across all prompts, languages, input types, or workflows.
Use a recent ComfyUI build with MiniMax-H3 and native INT8 ConvRot support. If you see unknown quantization-format, missing weight_scale, or ConvRot-related errors, update ComfyUI and its dependencies first.
Place the file in:
ComfyUI/models/text_encoders/
Download the matching MiniMax-H3 diffusion model and VAE files. The official ComfyUI repack is available at Comfy-Org/MiniMax-H3.
Select this file in the CLIPLoader node and keep the model type set to minimax.
If the file is not listed, verify that it is under models/text_encoders, not models/checkpoints or models/diffusion_models, then refresh the model list or restart ComfyUI.
This derivative may produce offensive, dangerous, illegal, misleading, or otherwise inappropriate content. Users are responsible for reviewing outputs, complying with applicable law and platform policies, and controlling how generated material is used or distributed. Do not use it to harm minors, violate privacy, commit fraud, promote hate, support military purposes, or engage in other illegal or harmful activity.
These weights are released under the Personal Entertainment Use License v1.0. They may be used only for personal entertainment, personal learning, non-commercial research, and non-commercial testing. Commercial use, paid services, commercial deployment, resale, redistribution, and sublicensing require prior written permission from linjian257.